In [1]:
suppressMessages(library(ArchR))
library(parallel)
library(rhdf5)
library(SingleCellExperiment)
library(SeuratDisk)
library(Seurat)
library(cowplot)
library(here)
ss <- function(x, pattern, slot = 1, ...) { sapply(strsplit(x = x, split = pattern, ...), '[', slot) }
options(stringsAsFactors = F)
options(repr.plot.width=11, repr.plot.height=8.5)

Registered S3 method overwritten by 'SeuratDisk':
  method            from  
  as.sparse.H5Group Seurat

Attaching SeuratObject


Attaching package: ‘Seurat’


The following object is masked from ‘package:SummarizedExperiment’:

    Assays


here() starts at /projects/pfenninggroup/singleCell/Macaque_SealDorsalHorn_snATAC-seq


Attaching package: ‘here’


The following object is masked from ‘package:plyr’:

    here
In [2]:
##################################
### set Arrow File parameters ####
addArchRThreads(threads = round(parallel::detectCores()*1/4))
#addArchRThreads(threads = 1)

##################################
### load rheMac10 ArchR genome ###
# GENOMEDIR='/home/bnphan/resources/genomes/rheMac10'
# load(file.path(GENOMEDIR,'rheMac10_liftoff_GRCh38.p13_ArchR_annotations.rda'))

addArchRGenome("mm10")

Setting default number of Parallel threads to 2.

Setting default genome to Mm10.
In [3]:
#correct neuron ArchRProject
PROJDIR='../../../data/tidy_data/ArchRProjects'
ARCHDIR=file.path(PROJDIR,'Mouse_scATAC_DorsalHorn_neuron2')
proj = loadArchRProject(ARCHDIR)
proj

#this project and *_neuron3 are unfinal
ARCHDIR=file.path(PROJDIR,'Mouse_scATAC_DorsalHorn_neuron')
proj2 = loadArchRProject(ARCHDIR)
proj2

Successfully loaded ArchRProject!


                                                   / |
                                                 /    \
            .                                  /      |.
            \\\                              /        |.
              \\\                          /           `|.
                \\\                      /              |.
                  \                    /                |\
                  \\#####\           /                  ||
                ==###########>      /                   ||
                 \\##==......\    /                     ||
            ______ =       =|__ /__                     ||      \\\
        ,--' ,----`-,__ ___/'  --,-`-===================##========>
       \               '        ##_______ _____ ,--,__,=##,__   ///
        ,    __==    ___,-,__,--'#'  ==='      `-'    | ##,-/
        -,____,---'       \\####\\________________,--\\_##,/
           ___      .______        ______  __    __  .______      
          /   \     |   _  \      /      ||  |  |  | |   _  \     
         /  ^  \    |  |_)  |    |  ,----'|  |__|  | |  |_)  |    
        /  /_\  \   |      /     |  |     |   __   | |      /     
       /  _____  \  |  |\  \\___ |  `----.|  |  |  | |  |\  \\___.
      /__/     \__\ | _| `._____| \______||__|  |__| | _| `._____|
    


           ___      .______        ______  __    __  .______      
          /   \     |   _  \      /      ||  |  |  | |   _  \     
         /  ^  \    |  |_)  |    |  ,----'|  |__|  | |  |_)  |    
        /  /_\  \   |      /     |  |     |   __   | |      /     
       /  _____  \  |  |\  \\___ |  `----.|  |  |  | |  |\  \\___.
      /__/     \__\ | _| `._____| \______||__|  |__| | _| `._____|
    


class: ArchRProject 
outputDirectory: /projects/pfenninggroup/singleCell/Macaque_SealDorsalHorn_snATAC-seq/data/tidy_data/ArchRProjects/Mouse_scATAC_DorsalHorn_neuron2 
samples(12): Mouse_DH_SEA2253A60 Mouse_DH_SEA2253A61 ...
  Mouse_DH_SEA2253A69 Mouse_DH_SEA2253A68
sampleColData names(8): ArrowFiles Sample_ID ... Species Region
cellColData names(39): Sample TSSEnrichment ...
  predictedGroup_RNA2ATAC_clustertype
  predictedScore_RNA2ATAC_clustertype
numberOfCells(1): 20591
medianTSS(1): 20.626
medianFrags(1): 25740
Successfully loaded ArchRProject!


                                                   / |
                                                 /    \
            .                                  /      |.
            \\\                              /        |.
              \\\                          /           `|.
                \\\                      /              |.
                  \                    /                |\
                  \\#####\           /                  ||
                ==###########>      /                   ||
                 \\##==......\    /                     ||
            ______ =       =|__ /__                     ||      \\\
        ,--' ,----`-,__ ___/'  --,-`-===================##========>
       \               '        ##_______ _____ ,--,__,=##,__   ///
        ,    __==    ___,-,__,--'#'  ==='      `-'    | ##,-/
        -,____,---'       \\####\\________________,--\\_##,/
           ___      .______        ______  __    __  .______      
          /   \     |   _  \      /      ||  |  |  | |   _  \     
         /  ^  \    |  |_)  |    |  ,----'|  |__|  | |  |_)  |    
        /  /_\  \   |      /     |  |     |   __   | |      /     
       /  _____  \  |  |\  \\___ |  `----.|  |  |  | |  |\  \\___.
      /__/     \__\ | _| `._____| \______||__|  |__| | _| `._____|
    


           ___      .______        ______  __    __  .______      
          /   \     |   _  \      /      ||  |  |  | |   _  \     
         /  ^  \    |  |_)  |    |  ,----'|  |__|  | |  |_)  |    
        /  /_\  \   |      /     |  |     |   __   | |      /     
       /  _____  \  |  |\  \\___ |  `----.|  |  |  | |  |\  \\___.
      /__/     \__\ | _| `._____| \______||__|  |__| | _| `._____|
    


class: ArchRProject 
outputDirectory: /projects/pfenninggroup/singleCell/Macaque_SealDorsalHorn_snATAC-seq/data/tidy_data/ArchRProjects/Mouse_scATAC_DorsalHorn_neuron 
samples(12): Mouse_DH_SEA2253A61 Mouse_DH_SEA2253A60 ...
  Mouse_DH_SEA2253A68 Mouse_DH_SEA2253A64
sampleColData names(8): ArrowFiles Sample_ID ... Species Region
cellColData names(31): Sample TSSEnrichment ...
  predictedScore_RNA2ATACCo ClustersX20
numberOfCells(1): 39059
medianTSS(1): 18.496
medianFrags(1): 30306
In [4]:
p1 <- plotEmbedding(ArchRProj = proj, colorBy = "cellColData", 
                    name = "ClustersX10", embedding = "UMAPX10")
p2 <- plotEmbedding(ArchRProj = proj, colorBy = "cellColData", 
                    name = "predictedGroup_RNA2ATACCo_cell", embedding = "UMAPX10")
ggAlignPlots(p1, p2, type = "h")

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-6a1e57ce717e2-Date-2023-01-31_Time-19-00-02.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.

Length of unique values greater than palette, interpolating..



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-6a1e57ce717e2-Date-2023-01-31_Time-19-00-02.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-6a1e5699a26e6-Date-2023-01-31_Time-19-00-46.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-6a1e5699a26e6-Date-2023-01-31_Time-19-00-46.log
In [ ]:
p1 <- plotEmbedding(ArchRProj = proj2, colorBy = "cellColData", 
                    name = "ClustersX20", embedding = "UMAPX20")
p2 <- plotEmbedding(ArchRProj = proj2, colorBy = "cellColData", 
                    name = "predictedGroup_RNA2ATACCo", embedding = "UMAPX20")
ggAlignPlots(p1, p2, type = "h")
In [ ]:
proj <- addImputeWeights(proj, reducedDims = "HarmonyX10")
# proj <- addImputeWeights(proj, reducedDims = "HarmonyX20")
In [4]:
head(getCellColData(proj))
class(getCellColData(proj))

DataFrame with 6 rows and 39 columns
                                                  Sample TSSEnrichment
                                             <character>     <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA Mouse_DH_SEA2253A58        14.164
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT Mouse_DH_SEA2253A58        15.910
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG Mouse_DH_SEA2253A58        10.861
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG Mouse_DH_SEA2253A58        17.269
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC Mouse_DH_SEA2253A58        18.201
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT Mouse_DH_SEA2253A58        13.550
                                     ReadsInTSS ReadsInPromoter
                                      <numeric>       <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA       6788           24952
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT       6990           25965
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG       4355           16936
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG       7718           27008
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC       7445           25859
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT       6268           22342
                                     ReadsInBlacklist PromoterRatio    PassQC
                                            <numeric>     <numeric> <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA             3777      0.155608         1
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT             3880      0.176551         1
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG             3561      0.115299         1
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG             4147      0.185642         1
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC             5408      0.183335         1
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT             2593      0.162353         1
                                     NucleosomeRatio nMultiFrags nMonoFrags
                                           <numeric>   <numeric>  <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA        0.919877        6002      41761
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT        1.359279        8719      31168
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG        1.350735        7665      31243
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG        0.868773        4609      38925
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC        0.883453        5368      37444
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT        0.704367        6233      40371
                                        nFrags  nDiFrags DoubletScore
                                     <numeric> <numeric>    <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA     80176     32413            0
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT     73534     33647            0
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG     73444     34536            0
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG     72742     29208            0
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC     70524     27712            0
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT     68807     22203            0
                                     DoubletEnrichment BlacklistRatio
                                             <numeric>      <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA         0.3000000      0.0235544
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT         0.0666667      0.0263824
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG         0.2666667      0.0242430
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG         0.4000000      0.0285049
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC         0.5666667      0.0383416
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT         0.3833333      0.0188426
                                       Sample_ID Date.nuclei.prep
                                     <character>      <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT  SEA2253A58       2022-02-15
                                     Biological.rep       Age         Sex
                                        <character> <numeric> <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT     Mouse01-10  0.134247    F/M pool
                                         Species      Region ClustersI200
                                     <character> <character>  <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC       Mouse  DorsalHorn           C9
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT       Mouse  DorsalHorn          C11
                                     ClustersH200 logNFrags   Celltype1
                                      <character> <numeric> <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA          C14   4.90404         EXC
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT          C11   4.86649         EXC
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG          C11   4.86596         EXC
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG          C11   4.86179         EXC
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC          C11   4.84834         EXC
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT          C14   4.83763         EXC
                                     ClustersX60 predictedCell_Co
                                     <character>      <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA          C6              564
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT          C9             2290
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG         C12                2
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG         C10             4496
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC         C16             1570
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT          C6             1394
                                     predictedGroup_RNA2ATACCo
                                                   <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                   midVent
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                   midVent
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                  Inh-Cdh3
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                   midVent
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                  Inh-Rorb
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT                   Ex-Sox5
                                     predictedScore_RNA2ATACCo ClustersX20
                                                     <numeric> <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                  0.893739          C4
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                  0.805882         C16
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                  0.931563         C11
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                  0.564452          C1
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                  0.537839         C13
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT                  0.721488          C4
                                     ClustersX10 predictedCell_Co_cell
                                     <character>           <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA         C24                   564
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT          C6                  2290
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG         C15                     2
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG         C18                  4496
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC         C17                  1570
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT         C24                  1394
                                     predictedGroup_RNA2ATACCo_cell
                                                        <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                         midVen
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                         midVen
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                          GABA1
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                         midVen
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                          GABA4
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT                          GLUT6
                                     predictedScore_RNA2ATACCo_cell
                                                          <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                       0.893739
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                       0.805882
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                       0.931563
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                       0.564452
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                       0.413136
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT                       0.340210
                                      Neuron_Type predictedCell_clustertype
                                      <character>               <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA      midVent                       877
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT      midVent                      2290
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG        GABA?                      1303
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG      midVent                      8064
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC GABA2_1, 4_1                      4865
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT  GLUT3,4,5,6                       564
                                     predictedGroup_RNA2ATAC_clustertype
                                                             <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                              midVen
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                              midVen
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                               GABA1
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                              midVen
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                              midVen
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT                              midVen
                                     predictedScore_RNA2ATAC_clustertype
                                                               <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                            1.000000
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                            0.948107
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                            0.850651
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                            0.408128
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                            0.475185
Mouse_DH_SEA2253A58#GGGTTGCTGCGACTAT                            0.361142
'DFrame'

Check clusters w/ lower nFrag (dead cells) and doublets¶

In [5]:
# make UMAP plots of
p1 <- plotEmbedding(ArchRProj = proj, colorBy = "cellColData", 
                    name = "ClustersX20", embedding = "UMAPX20")
p2 <- plotEmbedding(ArchRProj = proj, colorBy = "cellColData", 
                    name = "DoubletEnrichment", embedding = "UMAPX20")
ggAlignPlots(p1, p2, type = "h")


proj$logNFrags = log10(proj$nFrags)
p3 <- plotEmbedding(ArchRProj = proj, colorBy = "cellColData", 
                    name = "logNFrags", embedding = "UMAPX20")
p4 <- plotEmbedding(ArchRProj = proj, colorBy = "cellColData", 
                    name = "TSSEnrichment", embedding = "UMAPX20")
ggAlignPlots(p1, p3, type = "h")
ggAlignPlots(p1, p4, type = "h")

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-336423e32831d-Date-2022-10-11_Time-10-45-11.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.

Length of unique values greater than palette, interpolating..



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-336423e32831d-Date-2022-10-11_Time-10-45-11.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-33642392c94e2-Date-2022-10-11_Time-10-45-28.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 


ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-33642392c94e2-Date-2022-10-11_Time-10-45-28.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-33642690a9156-Date-2022-10-11_Time-10-45-36.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 


ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-33642690a9156-Date-2022-10-11_Time-10-45-36.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-33642d72462b-Date-2022-10-11_Time-10-45-39.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 


ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-33642d72462b-Date-2022-10-11_Time-10-45-39.log
In [6]:
p1 <- plotEmbedding(ArchRProj = proj, colorBy = "cellColData", 
                    name = "ClustersX10", embedding = "UMAPX10")
p2 <- plotEmbedding(ArchRProj = proj, colorBy = "cellColData", 
                    name = "DoubletEnrichment", embedding = "UMAPX10")
ggAlignPlots(p1, p2, type = "h")


proj$logNFrags = log10(proj$nFrags)
p3 <- plotEmbedding(ArchRProj = proj, colorBy = "cellColData", 
                    name = "logNFrags", embedding = "UMAPX10")
p4 <- plotEmbedding(ArchRProj = proj, colorBy = "cellColData", 
                    name = "TSSEnrichment", embedding = "UMAPX10")
ggAlignPlots(p1, p3, type = "h")
ggAlignPlots(p1, p4, type = "h")

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-3364277d82ea4-Date-2022-10-11_Time-10-45-49.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.

Length of unique values greater than palette, interpolating..



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-3364277d82ea4-Date-2022-10-11_Time-10-45-49.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-3364241088620-Date-2022-10-11_Time-10-45-51.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 


ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-3364241088620-Date-2022-10-11_Time-10-45-51.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-3364233d8eee7-Date-2022-10-11_Time-10-45-56.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 


ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-3364233d8eee7-Date-2022-10-11_Time-10-45-56.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-3364258713911-Date-2022-10-11_Time-10-45-57.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 


ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-3364258713911-Date-2022-10-11_Time-10-45-57.log

Integrate with snRNA-seq from neuronal cell types¶

In [6]:
##########################
# library(SingleCellExperiment)
# library(SeuratDisk)
neuron_data_sce = readRDS("/projects/pfenninggroup/singleCell/Macaque_SealDorsalHorn_snATAC-seq/data/tidy_data/rdas/macaque_integrated_neuronsv3.mouseGenes.sce.rds")
# neuron_data_sce = LoadH5Seurat("/projects/pfenninggroup/singleCell/Macaque_SealDorsalHorn_snATAC-seq/data/tidy_data/mmData.comp.adult.2fixerr.h5seurat",assays = "RNA")
# mmSeuratSr <- LoadH5Seurat(mmSeuratFn,assays = "RNA")
# neuron_data_sce[[]][1:5,]
# neuron_data_sce$RNA[1:5,1:5]
# index <- sce$cluster_type != "midVen"

# neuron_data_sce <- sce[,index]
# counts actually natural logcounts, undo first, use `counts` as RNA thing to co-cluster
# counts(neuron_data_sce) = 2.718 ^ logcounts(neuron_data_sce) - 1 
#logcounts(neuron_data_sce) = NULL # so only 1 assay available

# has cluster_type data
table(neuron_data_sce$cluster_type)

  GLUT1   GLUT2   GLUT3   GLUT4   GLUT5   GLUT6   GLUT7   GLUT8   GLUT9  GLUT10 
    142     222     152      49     105     123     124      76      98      62 
 GLUT11   GABA1 GABA2_1 GABA2_2   GABA3 GABA4_1 GABA4_2   GABA5  midVen 
     89     109      65      71      74      91     100     202     744
In [2]:
head(colData(neuron_data_sce))
table(colData(neuron_data_sce)$cell_type)
table(colData(neuron_data_sce)$cluster_type)

DataFrame with 6 rows and 23 columns
           Barcode Unnamed..0
          <factor>  <integer>
1 AAACCCAAGGATACGC          1
2 AAACCCAAGTAGGTTA          2
4 AAACGAAAGGTGATAT          4
5 AAACGAAGTACCAATC          5
7 AAACGAAGTCCTACGG          7
8 AAACGAAGTTGGGATG          8
                                                                                              Sample
                                                                                            <factor>
1 /projects/pfenninggroup/machineLearningForComputationalBiology/SingleCell/dorsal_horn/P0/Solo.out/
2 /projects/pfenninggroup/machineLearningForComputationalBiology/SingleCell/dorsal_horn/P0/Solo.out/
4 /projects/pfenninggroup/machineLearningForComputationalBiology/SingleCell/dorsal_horn/P0/Solo.out/
5 /projects/pfenninggroup/machineLearningForComputationalBiology/SingleCell/dorsal_horn/P0/Solo.out/
7 /projects/pfenninggroup/machineLearningForComputationalBiology/SingleCell/dorsal_horn/P0/Solo.out/
8 /projects/pfenninggroup/machineLearningForComputationalBiology/SingleCell/dorsal_horn/P0/Solo.out/
  cxds_score bcds_score hybrid_score precluster      nUMI     nGene
   <numeric>  <numeric>    <numeric>  <integer> <integer> <integer>
1     151403  0.1023747     0.258838          8     16448      5536
2     207183  0.0779373     0.303326          2     25551      7119
4     126729  0.0457364     0.165572         11     19303      6062
5     345115  0.3334055     0.757984          9     21247      6543
7     224653  0.2941971     0.561554          2     24462      7545
8     180312  0.0766830     0.267683          2     19649      6363
  sample_short           unique_id precluster_sample size_factor   leiden
      <factor>         <character>          <factor>   <numeric> <factor>
1           P0 AAACCCAAGGATACGC_P0             8_P0      3.71738       10
2           P0 AAACCCAAGTAGGTTA_P0             2_P0      5.91423       11
4           P0 AAACGAAAGGTGATAT_P0             11_P0     4.29774       3 
5           P0 AAACGAAGTACCAATC_P0             9_P0      5.00223       7 
7           P0 AAACGAAGTCCTACGG_P0             2_P0      6.25127       0 
8           P0 AAACGAAGTTGGGATG_P0             2_P0      4.71166       0 
   clust_2 cell_type cluster_type  mouse_class pred_mm_class_label mouse_family
  <factor>  <factor>     <factor>     <factor>            <factor>     <factor>
1       28    GLUT6        GLUT6  dorsal_excit        dorsal_excit     Ex-Sox5 
2       6     GABA1        GABA1  dorsal_inhib        dorsal_inhib     Inh-Cdh3
4       26    GABA5        GABA5  dorsal_inhib        midVent          Inh-Pdyn
5       11    GLUT1        GLUT1  dorsal_excit        midVent          Ex-Reln 
7       21    midVen       midVen midVent             midVent          midVent 
8       20    midVen       midVen midVent             midVent          midVent 
  nCount_RNA nFeature_RNA    ident
   <numeric>    <integer> <factor>
1      20261        16692  AnnData
2      20052        16692  AnnData
4      19517        16692  AnnData
5      19602        16692  AnnData
7      18977        16692  AnnData
8      19448        16692  AnnData
 GLUT1  GLUT2  GLUT3  GLUT4  GLUT5  GLUT6  GLUT7  GLUT8  GLUT9 GLUT10 GLUT11 
   142    222    152     49    105    123    124     76     98     62     89 
 GABA1  GABA2  GABA3  GABA4  GABA5 midVen 
   109    136     74    191    202    744 
  GLUT1   GLUT2   GLUT3   GLUT4   GLUT5   GLUT6   GLUT7   GLUT8   GLUT9  GLUT10 
    142     222     152      49     105     123     124      76      98      62 
 GLUT11   GABA1 GABA2_1 GABA2_2   GABA3 GABA4_1 GABA4_2   GABA5  midVen 
     89     109      65      71      74      91     100     202     744
In [ ]:
#####################################
# integration split by tissue region  ##Vijay: These are the mouse gene families from the Levine paper I assume
proj = addGeneIntegrationMatrix(
  ArchRProj = proj, 
  useMatrix = "GeneScoreMatrix", 
  matrixName = "GeneIntegrationMatrix", 
  reducedDims = "HarmonyX10", 
  seRNA = neuron_data_sce, nGenes = 2000, 
  addToArrow = TRUE, plotUMAP = TRUE, 
  groupRNA = "mouse_family", 
  nameCell = "predictedCell_Co", 
  nameGroup = "predictedGroup_RNA2ATACCo", 
  nameScore = "predictedScore_RNA2ATACCo",
  force = TRUE)

proj = saveArchRProject(ArchRProj = proj)
In [6]:
#####################################
# integration split by tissue region ##Vijay: These are the macaque cell types
proj = addGeneIntegrationMatrix(
  ArchRProj = proj, 
  useMatrix = "GeneScoreMatrix", 
  matrixName = "GeneIntegrationMatrix1", 
  reducedDims = "HarmonyX10", 
  seRNA = neuron_data_sce, nGenes = 2000, 
  addToArrow = TRUE, plotUMAP = TRUE, 
  groupRNA = "cell_type", 
  nameCell = "predictedCell_Co_cell", 
  nameGroup = "predictedGroup_RNA2ATACCo_cell", 
  nameScore = "predictedScore_RNA2ATACCo_cell",
  force = TRUE)

proj = saveArchRProject(ArchRProj = proj)

ArchR logging to : ArchRLogs/ArchR-addGeneIntegrationMatrix-b52c6a56c69a-Date-2022-10-07_Time-15-25-48.log
If there is an issue, please report to github with logFile!

2022-10-07 15:25:49 : Running Seurat's Integration Stuart* et al 2019, 0.003 mins elapsed.

2022-10-07 15:25:50 : Checking ATAC Input, 0.034 mins elapsed.

2022-10-07 15:27:04 : Checking RNA Input, 1.26 mins elapsed.

2022-10-07 15:27:14 : Found 15939 overlapping gene names from gene scores and rna matrix!, 1.42 mins elapsed.

2022-10-07 15:27:14 : Creating Integration Blocks, 1.42 mins elapsed.

2022-10-07 15:27:14 : Prepping Interation Data, 1.421 mins elapsed.

2022-10-07 15:27:17 : Computing Integration in 2 Integration Blocks!, 0 mins elapsed.

2022-10-07 15:27:17 : Block (1 of 2) : Computing Integration, 0 mins elapsed.

2022-10-07 15:27:20 : Block (1 of 2) : Identifying Variable Genes, 0.064 mins elapsed.

2022-10-07 15:27:28 : Block (1 of 2) : Getting GeneScoreMatrix, 0.197 mins elapsed.

2022-10-07 15:29:06 : Block (1 of 2) : Imputing GeneScoreMatrix, 1.826 mins elapsed.

Getting ImputeWeights

2022-10-07 15:30:37 : Block (1 of 2) : Seurat FindTransferAnchors, 3.342 mins elapsed.

2022-10-07 15:31:21 : Block (1 of 2) : Seurat TransferData Cell Group Labels, 4.077 mins elapsed.

2022-10-07 15:31:23 : Block (1 of 2) : Seurat TransferData Cell Names Labels, 4.115 mins elapsed.

2022-10-07 15:31:30 : Block (1 of 2) : Seurat TransferData GeneMatrix, 4.217 mins elapsed.

2022-10-07 15:32:09 : Block (1 of 2) : Saving TransferAnchors Joint CCA, 4.877 mins elapsed.

2022-10-07 15:32:11 : Block (1 of 2) : Transferring Paired RNA to Temp File, 4.899 mins elapsed.

2022-10-07 15:33:19 : Block (1 of 2) : Completed Integration, 6.04 mins elapsed.

2022-10-07 15:33:20 : Block (2 of 2) : Computing Integration, 6.057 mins elapsed.

2022-10-07 15:33:23 : Block (2 of 2) : Identifying Variable Genes, 6.116 mins elapsed.

2022-10-07 15:33:33 : Block (2 of 2) : Getting GeneScoreMatrix, 6.269 mins elapsed.

2022-10-07 15:35:49 : Block (2 of 2) : Imputing GeneScoreMatrix, 8.546 mins elapsed.

Getting ImputeWeights

2022-10-07 15:37:48 : Block (2 of 2) : Seurat FindTransferAnchors, 10.517 mins elapsed.

2022-10-07 15:38:26 : Block (2 of 2) : Seurat TransferData Cell Group Labels, 11.149 mins elapsed.

2022-10-07 15:38:28 : Block (2 of 2) : Seurat TransferData Cell Names Labels, 11.189 mins elapsed.

2022-10-07 15:38:34 : Block (2 of 2) : Seurat TransferData GeneMatrix, 11.297 mins elapsed.

2022-10-07 15:39:14 : Block (2 of 2) : Saving TransferAnchors Joint CCA, 11.96 mins elapsed.

2022-10-07 15:39:15 : Block (2 of 2) : Transferring Paired RNA to Temp File, 11.979 mins elapsed.

2022-10-07 15:40:14 : Block (2 of 2) : Completed Integration, 12.96 mins elapsed.

2022-10-07 15:40:15 : Block (1 of 2) : Plotting Joint UMAP, 12.975 mins elapsed.

WARNING: Error found with Cairo installation. Continuing without rasterization.

WARNING: Error found with Cairo installation. Continuing without rasterization.

2022-10-07 15:40:53 : Block (2 of 2) : Plotting Joint UMAP, 13.601 mins elapsed.

WARNING: Error found with Cairo installation. Continuing without rasterization.

WARNING: Error found with Cairo installation. Continuing without rasterization.

2022-10-07 15:41:29 : Transferring Data to ArrowFiles, 14.202 mins elapsed.

2022-10-07 15:41:29 : Mouse_DH_SEA2253A60 (1 of 12) Getting GeneIntegrationMatrix From TempFiles!, 14.208 mins elapsed.

2022-10-07 15:41:47 : Mouse_DH_SEA2253A60 (1 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 14.51 mins elapsed.

2022-10-07 15:44:00 : Mouse_DH_SEA2253A62 (3 of 12) Getting GeneIntegrationMatrix From TempFiles!, 16.727 mins elapsed.

2022-10-07 15:44:18 : Mouse_DH_SEA2253A62 (3 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 17.024 mins elapsed.

2022-10-07 15:45:32 : Mouse_DH_SEA2253A59 (4 of 12) Getting GeneIntegrationMatrix From TempFiles!, 18.253 mins elapsed.

2022-10-07 15:45:58 : Mouse_DH_SEA2253A59 (4 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 18.687 mins elapsed.

2022-10-07 15:47:04 : Mouse_DH_SEA2253A58 (5 of 12) Getting GeneIntegrationMatrix From TempFiles!, 19.799 mins elapsed.

2022-10-07 15:47:21 : Mouse_DH_SEA2253A58 (5 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 20.072 mins elapsed.

2022-10-07 15:48:08 : Mouse_DH_SEA2253A66 (6 of 12) Getting GeneIntegrationMatrix From TempFiles!, 20.856 mins elapsed.

2022-10-07 15:48:21 : Mouse_DH_SEA2253A66 (6 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 21.068 mins elapsed.

2022-10-07 15:49:02 : Mouse_DH_SEA2253A63 (7 of 12) Getting GeneIntegrationMatrix From TempFiles!, 21.756 mins elapsed.

2022-10-07 15:49:19 : Mouse_DH_SEA2253A63 (7 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 22.049 mins elapsed.

2022-10-07 15:50:12 : Mouse_DH_SEA2253A67 (8 of 12) Getting GeneIntegrationMatrix From TempFiles!, 22.93 mins elapsed.

2022-10-07 15:50:24 : Mouse_DH_SEA2253A67 (8 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 23.125 mins elapsed.

2022-10-07 15:51:09 : Mouse_DH_SEA2253A65 (9 of 12) Getting GeneIntegrationMatrix From TempFiles!, 23.869 mins elapsed.

2022-10-07 15:51:20 : Mouse_DH_SEA2253A65 (9 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 24.051 mins elapsed.

2022-10-07 15:52:06 : Mouse_DH_SEA2253A64 (10 of 12) Getting GeneIntegrationMatrix From TempFiles!, 24.816 mins elapsed.

2022-10-07 15:52:18 : Mouse_DH_SEA2253A64 (10 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 25.026 mins elapsed.

2022-10-07 15:53:03 : Mouse_DH_SEA2253A69 (11 of 12) Getting GeneIntegrationMatrix From TempFiles!, 25.768 mins elapsed.

2022-10-07 15:53:12 : Mouse_DH_SEA2253A69 (11 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 25.925 mins elapsed.

2022-10-07 15:53:58 : Mouse_DH_SEA2253A68 (12 of 12) Getting GeneIntegrationMatrix From TempFiles!, 26.687 mins elapsed.

2022-10-07 15:54:07 : Mouse_DH_SEA2253A68 (12 of 12) Adding GeneIntegrationMatrix to ArrowFile!, 26.849 mins elapsed.

2022-10-07 15:54:59 : Completed Integration with RNA Matrix, 27.708 mins elapsed.

ArchR logging successful to : ArchRLogs/ArchR-addGeneIntegrationMatrix-b52c6a56c69a-Date-2022-10-07_Time-15-25-48.log

Saving ArchRProject...

Loading ArchRProject...

Successfully loaded ArchRProject!


                                                   / |
                                                 /    \
            .                                  /      |.
            \\\                              /        |.
              \\\                          /           `|.
                \\\                      /              |.
                  \                    /                |\
                  \\#####\           /                  ||
                ==###########>      /                   ||
                 \\##==......\    /                     ||
            ______ =       =|__ /__                     ||      \\\
        ,--' ,----`-,__ ___/'  --,-`-===================##========>
       \               '        ##_______ _____ ,--,__,=##,__   ///
        ,    __==    ___,-,__,--'#'  ==='      `-'    | ##,-/
        -,____,---'       \\####\\________________,--\\_##,/
           ___      .______        ______  __    __  .______      
          /   \     |   _  \      /      ||  |  |  | |   _  \     
         /  ^  \    |  |_)  |    |  ,----'|  |__|  | |  |_)  |    
        /  /_\  \   |      /     |  |     |   __   | |      /     
       /  _____  \  |  |\  \\___ |  `----.|  |  |  | |  |\  \\___.
      /__/     \__\ | _| `._____| \______||__|  |__| | _| `._____|
In [7]:
#####################################
#integration split by tissue region 
proj = addGeneIntegrationMatrix(
  ArchRProj = proj, 
  useMatrix = "GeneScoreMatrix", 
  matrixName = "GeneIntegrationMatrix1", 
  reducedDims = "HarmonyX10", 
  seRNA = neuron_data_sce, nGenes = 2000, 
  addToArrow = TRUE, plotUMAP = TRUE, 
  groupRNA = "cluster_type", 
  nameCell = "predictedCell_clustertype", 
  nameGroup = "predictedGroup_RNA2ATAC_clustertype", 
  nameScore = "predictedScore_RNA2ATAC_clustertype",
  force = TRUE)

# proj = saveArchRProject(ArchRProj = proj)

ArchR logging to : ArchRLogs/ArchR-addGeneIntegrationMatrix-6a1e54ee9c6f2-Date-2023-01-31_Time-19-04-56.log
If there is an issue, please report to github with logFile!

2023-01-31 19:04:59 : Running Seurat's Integration Stuart* et al 2019, 0.054 mins elapsed.

2023-01-31 19:05:01 : Checking ATAC Input, 0.092 mins elapsed.

2023-01-31 19:05:51 : Checking RNA Input, 0.919 mins elapsed.

2023-01-31 19:05:57 : Found 15939 overlapping gene names from gene scores and rna matrix!, 1.02 mins elapsed.

2023-01-31 19:05:59 : Creating Integration Blocks, 1.051 mins elapsed.

2023-01-31 19:05:59 : Prepping Interation Data, 1.052 mins elapsed.

2023-01-31 19:06:00 : Computing Integration in 2 Integration Blocks!, 0 mins elapsed.

2023-01-31 19:13:26 : Block (1 of 2) : Plotting Joint UMAP, 7.43 mins elapsed.

WARNING: Error found with Cairo installation. Continuing without rasterization.

WARNING: Error found with Cairo installation. Continuing without rasterization.

2023-01-31 19:14:04 : Block (2 of 2) : Plotting Joint UMAP, 8.07 mins elapsed.

WARNING: Error found with Cairo installation. Continuing without rasterization.

WARNING: Error found with Cairo installation. Continuing without rasterization.

2023-01-31 19:14:48 : Transferring Data to ArrowFiles, 8.79 mins elapsed.

2023-01-31 19:27:54 : Completed Integration with RNA Matrix, 21.902 mins elapsed.

ArchR logging successful to : ArchRLogs/ArchR-addGeneIntegrationMatrix-6a1e54ee9c6f2-Date-2023-01-31_Time-19-04-56.log
In [1]:
getCellColData(proj)

Error in getCellColData(proj): could not find function "getCellColData"
Traceback:

Compare snATAC clusters w/ snRNA clusters¶

In [13]:
cM <- confusionMatrix(paste0(proj$predictedGroup_RNA2ATACCo), paste0(proj$ClustersX10))
cM <- cM / Matrix::colSums(cM)
cM = cM[,order(colnames(cM))]
p <- pheatmap::pheatmap(
  mat = as.matrix(cM), 
  color = paletteContinuous("whiteBlue"), 
  border_color = "black")
p
In [56]:
cM <- confusionMatrix(paste0(proj$predictedGroup_RNA2ATACCo_cell), paste0(proj$predictedGroup_RNA2ATAC_clustertype))
cM <- cM / Matrix::colSums(cM)
cM = cM[,order(colnames(cM))]
p <- pheatmap::pheatmap(
  mat = as.matrix(cM), 
  color = paletteContinuous("whiteBlue"), 
  border_color = "black")
p
In [59]:
p1 <- plotEmbedding( proj, colorBy = "cellColData", name = "predictedGroup_RNA2ATACCo_cell", embedding = "UMAPX10")
p2 <- plotEmbedding( proj, colorBy = "cellColData", name = "predictedGroup_RNA2ATAC_clustertype", embedding = "UMAPX10")
p3 <- plotEmbedding( proj, colorBy = "cellColData", name = "ClustersX10", embedding = "UMAPX10")

ggAlignPlots(p3, p2, p1, type = "h")

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-6a1e520ed92de-Date-2023-01-31_Time-20-48-41.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-6a1e520ed92de-Date-2023-01-31_Time-20-48-41.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-6a1e53409a3dc-Date-2023-01-31_Time-20-49-18.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-6a1e53409a3dc-Date-2023-01-31_Time-20-49-18.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-6a1e553d05c05-Date-2023-01-31_Time-20-49-24.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.

Length of unique values greater than palette, interpolating..



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-6a1e553d05c05-Date-2023-01-31_Time-20-49-24.log
In [9]:
## Marker Genes for differentiation of Inhibitory Nuerons
markerGenes1  <- c('MASP1', # GABA 1
#                    'GDNF-AS1', # GABA 2
                   'RREB1', # GABA 2
                   'NPY', # GABA 3
                   'MET', # GABA 4
                   'PTN', # GABA 4
                   'PDYN' # GABA 5
                  )

p <- plotEmbedding( ArchRProj = proj, colorBy = "GeneScoreMatrix", 
                    name = markerGenes1, embedding = "UMAPX10")
p <- lapply(p, function(x){
  x + guides(color = FALSE, fill = FALSE) + 
    theme_ArchR(baseSize = 6.5) + theme(plot.margin = unit(c(0, 0, 0, 0), "cm")) +
    theme(  axis.text.x=element_blank(),  axis.ticks.x=element_blank(), 
            axis.text.y=element_blank(),  axis.ticks.y=element_blank())
})
do.call(cowplot::plot_grid, c(list(ncol = 3),p))

Getting ImputeWeights

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-336422b6c1765-Date-2022-10-11_Time-10-48-45.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = GeneScoreMatrix

Getting Matrix Values...

2022-10-11 10:48:46 : 

1 
2 
3 
4 
5 
6 
7 
8 
9 
10 
11 
12 


Imputing Matrix

Using weights on disk

1 of 4

2 of 4

3 of 4

4 of 4

Using weights on disk

1 of 4

2 of 4

3 of 4

4 of 4

Plotting Embedding

1 
2 
3 
4 
5 
6 


ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-336422b6c1765-Date-2022-10-11_Time-10-48-45.log

Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
In [10]:
## Marker Genes for differentiation of Excitatory Neurons
markerGenes1  <- c('GFRA1', #GLUT 1,2
#                    'TAC3', #GLUT 3,4
                   'GHR', #GLUT 5,6
                   'TAC1', #GLUT 6
                   'ADARB2', #GLUT 7-10 
                   'MAF', #GLUT 7
                   'ST8SIA6', #GLUT 8
                   'NTNG1', #GLUT 9,10
                   'SOX5' #GLUT6,6?
                  )

p <- plotEmbedding( ArchRProj = proj, colorBy = "GeneScoreMatrix", 
                    name = markerGenes1, embedding = "UMAPX10")
p <- lapply(p, function(x){
  x + guides(color = FALSE, fill = FALSE) + 
    theme_ArchR(baseSize = 6.5) + theme(plot.margin = unit(c(0, 0, 0, 0), "cm")) +
    theme(  axis.text.x=element_blank(),  axis.ticks.x=element_blank(), 
            axis.text.y=element_blank(),  axis.ticks.y=element_blank())
})
do.call(cowplot::plot_grid, c(list(ncol = 3),p))

Getting ImputeWeights

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-336425e10ad8c-Date-2022-10-11_Time-10-50-02.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = GeneScoreMatrix

Getting Matrix Values...

2022-10-11 10:50:04 : 

1 
2 
3 
4 
5 
6 
7 
8 
9 
10 
11 
12 


Imputing Matrix

Using weights on disk

1 of 4

2 of 4

3 of 4

4 of 4

Using weights on disk

1 of 4

2 of 4

3 of 4

4 of 4

Plotting Embedding

1 
2 
3 
4 
5 
6 
7 
8 


ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-336425e10ad8c-Date-2022-10-11_Time-10-50-02.log

Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
In [11]:
## Marker Genes for differentiation of Excitatory Neurons
markerGenes1  <- c('COL24A1', #GLUT 5
                   'CRHR2', #GLUT 1
                   'COL13A1', #GLUT 1
                   'NMUR2', #GLUT 2
                   'NMU', #GLUT 3
                   'COL5A2', #GLUT 4
                   'NMBR', #GLUT 5
                   'TAC1' #GLUT 6
#                    'ANOS1' #GLUT 6
                  )

p <- plotEmbedding( ArchRProj = proj, colorBy = "GeneScoreMatrix", 
                    name = markerGenes1, embedding = "UMAPX10")
p <- lapply(p, function(x){
  x + guides(color = FALSE, fill = FALSE) + 
    theme_ArchR(baseSize = 6.5) + theme(plot.margin = unit(c(0, 0, 0, 0), "cm")) +
    theme(  axis.text.x=element_blank(),  axis.ticks.x=element_blank(), 
            axis.text.y=element_blank(),  axis.ticks.y=element_blank())
})
do.call(cowplot::plot_grid, c(list(ncol = 3),p))

Getting ImputeWeights

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-336423f0333f-Date-2022-10-11_Time-10-51-22.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = GeneScoreMatrix

Getting Matrix Values...

2022-10-11 10:51:24 : 

1 
2 
3 
4 
5 
6 
7 
8 
9 
10 
11 
12 


Imputing Matrix

Using weights on disk

1 of 4

2 of 4

3 of 4

4 of 4

Using weights on disk

1 of 4

2 of 4

3 of 4

4 of 4

Plotting Embedding

1 
2 
3 
4 
5 
6 
7 
8 


ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-336423f0333f-Date-2022-10-11_Time-10-51-22.log

Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
Warning message:
“`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.”
In [14]:
## Marker Genes for differentiation of Excitatory Neurons
markerGenes1  <- c('COL21A1', #GLUT 7
                   'MAF', #GLUT 7
                   'MAFA', #GLUT 8
                   'ADAMTS16', #GLUT 9
                   'TLL2', #GLUT 9
                   'OTOGL', #GLUT 10
                   'PDYN' #GLUT 11
                  )

p <- plotEmbedding( ArchRProj = proj, colorBy = "GeneScoreMatrix", 
                    name = markerGenes1, embedding = "UMAPX10")
p <- lapply(p, function(x){
  x + guides(color = FALSE, fill = FALSE) + 
    theme_ArchR(baseSize = 6.5) + theme(plot.margin = unit(c(0, 0, 0, 0), "cm")) +
    theme(  axis.text.x=element_blank(),  axis.ticks.x=element_blank(), 
            axis.text.y=element_blank(),  axis.ticks.y=element_blank())
})
do.call(cowplot::plot_grid, c(list(ncol = 3),p))

Getting ImputeWeights

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-3364272610c0c-Date-2022-10-11_Time-10-54-36.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = GeneScoreMatrix

Getting Matrix Values...

2022-10-11 10:54:37 : 

FeatureName (COL21A1) does not exist! See getFeatures


Error: 

Traceback:

1. plotEmbedding(ArchRProj = proj, colorBy = "GeneScoreMatrix", 
 .     name = markerGenes1, embedding = "UMAPX10")
2. .getMatrixValues(ArchRProj = ArchRProj, name = name, matrixName = colorBy, 
 .     log2Norm = FALSE, threads = threads, logFile = logFile)
3. .logStop(sprintf("FeatureName (%s) does not exist! See getFeatures", 
 .     paste0(name[which(is.na(idx))], collapse = ",")), logFile = logFile)
4. stop(sprintf("%s\n", msg), call. = FALSE)
In [7]:
p1 <- plotEmbedding( proj, colorBy = "cellColData", name = "predictedGroup_RNA2ATAC_clustertype", embedding = "UMAPX10")
p2 <- plotEmbedding( proj, colorBy = "cellColData", name = "predictedGroup_RNA2ATACCo", embedding = "UMAPX10")
p3 <- plotEmbedding( proj, colorBy = "cellColData", name = "predictedGroup_RNA2ATACCo_cell", embedding = "UMAPX10")
p4 <- plotEmbedding( proj, colorBy = "cellColData", name = "ClustersX10", embedding = "UMAPX10")

plot_grid(p1, p2, p3, p4)

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-42341bd3684d-Date-2023-02-15_Time-10-23-58.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-42341bd3684d-Date-2023-02-15_Time-10-23-58.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-42341f695b9d-Date-2023-02-15_Time-10-24-00.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-42341f695b9d-Date-2023-02-15_Time-10-24-00.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-4234150d9f18-Date-2023-02-15_Time-10-24-02.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-4234150d9f18-Date-2023-02-15_Time-10-24-02.log

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-42341cc39d43-Date-2023-02-15_Time-10-24-04.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.

Length of unique values greater than palette, interpolating..



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-42341cc39d43-Date-2023-02-15_Time-10-24-04.log
In [8]:
#final cluster w/ RNA labels embedding
p3 <- plotEmbedding( proj, colorBy = "cellColData", name = "predictedGroup_RNA2ATAC_clustertype", embedding = "UMAPX10")
p3

ArchR logging to : ArchRLogs/ArchR-plotEmbedding-4234473d20f2-Date-2023-02-15_Time-10-24-17.log
If there is an issue, please report to github with logFile!

Getting UMAP Embedding

ColorBy = cellColData

Plotting Embedding

1 
WARNING: Error found with Cairo installation. Continuing without rasterization.



ArchR logging successful to : ArchRLogs/ArchR-plotEmbedding-4234473d20f2-Date-2023-02-15_Time-10-24-17.log
In [15]:
# drop the UNK cluster
idxSample <- BiocGenerics::which(proj$predictedGroup_RNA2ATACCo %ni% c('Drop'))
table(proj$predictedGroup_RNA2ATACCo[idxSample])
cellsSample <- proj$cellNames[idxSample]
proj = subsetCells(ArchRProj = proj, cellNames = cellsSample)
proj = saveArchRProject(ArchRProj = proj)
In [9]:
#add FINAL LABELS column to all projects
proj <- addCellColData(ArchRProj = proj, data = proj$predictedGroup_RNA2ATAC_clustertype,
    cells = rownames(getCellColData(proj)), name = "FINAL_GROUP_LABEL", force = TRUE)
names(getCellColData(proj))
getCellColData(proj)
  1. 'Sample'
  2. 'TSSEnrichment'
  3. 'ReadsInTSS'
  4. 'ReadsInPromoter'
  5. 'ReadsInBlacklist'
  6. 'PromoterRatio'
  7. 'PassQC'
  8. 'NucleosomeRatio'
  9. 'nMultiFrags'
  10. 'nMonoFrags'
  11. 'nFrags'
  12. 'nDiFrags'
  13. 'DoubletScore'
  14. 'DoubletEnrichment'
  15. 'BlacklistRatio'
  16. 'Sample_ID'
  17. 'Date.nuclei.prep'
  18. 'Biological.rep'
  19. 'Age'
  20. 'Sex'
  21. 'Species'
  22. 'Region'
  23. 'ClustersI200'
  24. 'ClustersH200'
  25. 'logNFrags'
  26. 'Celltype1'
  27. 'ClustersX60'
  28. 'predictedCell_Co'
  29. 'predictedGroup_RNA2ATACCo'
  30. 'predictedScore_RNA2ATACCo'
  31. 'ClustersX20'
  32. 'ClustersX10'
  33. 'predictedCell_Co_cell'
  34. 'predictedGroup_RNA2ATACCo_cell'
  35. 'predictedScore_RNA2ATACCo_cell'
  36. 'Neuron_Type'
  37. 'predictedCell_clustertype'
  38. 'predictedGroup_RNA2ATAC_clustertype'
  39. 'predictedScore_RNA2ATAC_clustertype'
  40. 'FINAL_GROUP_LABEL'
DataFrame with 20591 rows and 40 columns
                                                  Sample TSSEnrichment
                                             <character>     <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA Mouse_DH_SEA2253A58        14.164
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT Mouse_DH_SEA2253A58        15.910
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG Mouse_DH_SEA2253A58        10.861
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG Mouse_DH_SEA2253A58        17.269
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC Mouse_DH_SEA2253A58        18.201
...                                                  ...           ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG Mouse_DH_SEA2253A69         8.303
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG Mouse_DH_SEA2253A69         9.596
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC Mouse_DH_SEA2253A69        50.724
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG Mouse_DH_SEA2253A69        31.498
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT Mouse_DH_SEA2253A69        30.471
                                     ReadsInTSS ReadsInPromoter
                                      <numeric>       <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA       6788           24952
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT       6990           25965
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG       4355           16936
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG       7718           27008
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC       7445           25859
...                                         ...             ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG        348            1581
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG        378            1668
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC       1332            3902
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG       1193            3754
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT        754            2477
                                     ReadsInBlacklist PromoterRatio    PassQC
                                            <numeric>     <numeric> <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA             3777      0.155608         1
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT             3880      0.176551         1
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG             3561      0.115299         1
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG             4147      0.185642         1
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC             5408      0.183335         1
...                                               ...           ...       ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG              244      0.117094         1
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG              202      0.128052         1
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC              340      0.301966         1
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG              240      0.302742         1
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT              247      0.256365         1
                                     NucleosomeRatio nMultiFrags nMonoFrags
                                           <numeric>   <numeric>  <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA        0.919877        6002      41761
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT        1.359279        8719      31168
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG        1.350735        7665      31243
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG        0.868773        4609      38925
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC        0.883453        5368      37444
...                                              ...         ...        ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG        6.054336        1442        957
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG        8.808735        1299        664
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC        0.137300         189       5681
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG        0.130562         152       5484
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT        0.661279         368       2908
                                        nFrags  nDiFrags DoubletScore
                                     <numeric> <numeric>    <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA     80176     32413            0
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT     73534     33647            0
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG     73444     34536            0
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG     72742     29208            0
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC     70524     27712            0
...                                        ...       ...          ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG      6751      4352            0
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG      6513      4550            0
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC      6461       591            0
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG      6200       564            0
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT      4831      1555            0
                                     DoubletEnrichment BlacklistRatio
                                             <numeric>      <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA         0.3000000      0.0235544
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT         0.0666667      0.0263824
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG         0.2666667      0.0242430
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG         0.4000000      0.0285049
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC         0.5666667      0.0383416
...                                                ...            ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG         1.0222222      0.0180714
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG         0.2222222      0.0155074
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC         0.0222222      0.0263117
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG         0.0000000      0.0193548
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT         0.2000000      0.0255641
                                       Sample_ID Date.nuclei.prep
                                     <character>      <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC  SEA2253A58       2022-02-15
...                                          ...              ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG  SEA2253A69       2022-02-23
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG  SEA2253A69       2022-02-23
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC  SEA2253A69       2022-02-23
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG  SEA2253A69       2022-02-23
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT  SEA2253A69       2022-02-23
                                     Biological.rep       Age         Sex
                                        <character> <numeric> <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC     Mouse01-10  0.134247    F/M pool
...                                             ...       ...         ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG     Mouse11-20  0.156164    F/M pool
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG     Mouse11-20  0.156164    F/M pool
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC     Mouse11-20  0.156164    F/M pool
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG     Mouse11-20  0.156164    F/M pool
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT     Mouse11-20  0.156164    F/M pool
                                         Species      Region ClustersI200
                                     <character> <character>  <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC       Mouse  DorsalHorn           C9
...                                          ...         ...          ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG       Mouse  DorsalHorn          C14
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG       Mouse  DorsalHorn           C5
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC       Mouse  DorsalHorn          C15
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG       Mouse  DorsalHorn          C15
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT       Mouse  DorsalHorn          C15
                                     ClustersH200 logNFrags   Celltype1
                                      <character> <numeric> <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA          C14   4.90404         EXC
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT          C11   4.86649         EXC
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG          C11   4.86596         EXC
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG          C11   4.86179         EXC
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC          C11   4.84834         EXC
...                                           ...       ...         ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG          C14   3.82937         EXC
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG           C7   3.81378         INH
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC          C15   3.81030         EXC
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG          C15   3.79239         EXC
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT          C15   3.68404         EXC
                                     ClustersX60 predictedCell_Co
                                     <character>      <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA          C6              564
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT          C9             2290
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG         C12                2
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG         C10             4496
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC         C16             1570
...                                          ...              ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG         C22            10242
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG         C17             8674
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC         C20             8839
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG         C20             1590
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT         C20             8839
                                     predictedGroup_RNA2ATACCo
                                                   <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                   midVent
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                   midVent
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                  Inh-Cdh3
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                   midVent
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                  Inh-Rorb
...                                                        ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG                   Ex-Sox5
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG               Inh-Adamts5
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC                   Ex-Reln
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG                   Ex-Reln
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT                   Ex-Reln
                                     predictedScore_RNA2ATACCo ClustersX20
                                                     <numeric> <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                  0.893739          C4
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                  0.805882         C16
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                  0.931563         C11
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                  0.564452          C1
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                  0.537839         C13
...                                                        ...         ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG                  0.665456         C18
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG                  0.949357         C14
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC                  0.819760         C25
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG                  0.991770         C25
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT                  0.881383         C25
                                     ClustersX10 predictedCell_Co_cell
                                     <character>           <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA         C24                   564
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT          C6                  2290
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG         C15                     2
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG         C18                  4496
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC         C17                  1570
...                                          ...                   ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG         C11                 10242
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG         C13                  8674
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC          C5                  8839
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG          C5                  1590
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT          C5                  8839
                                     predictedGroup_RNA2ATACCo_cell
                                                        <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                         midVen
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                         midVen
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                          GABA1
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                         midVen
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                          GABA4
...                                                             ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG                          GLUT4
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG                          GABA4
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC                          GLUT2
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG                          GLUT2
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT                          GLUT2
                                     predictedScore_RNA2ATACCo_cell
                                                          <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                       0.893739
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                       0.805882
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                       0.931563
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                       0.564452
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                       0.413136
...                                                             ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG                       0.551314
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG                       0.918794
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC                       0.636967
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG                       0.909557
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT                       0.705046
                                      Neuron_Type predictedCell_clustertype
                                      <character>               <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA      midVent                       877
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT      midVent                      2290
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG        GABA?                      1303
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG      midVent                      8064
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC GABA2_1, 4_1                      4865
...                                           ...                       ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG  GLUT3,4,5,6                     11604
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG GABA2_2, 4_2                      8674
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC      GLUT1,2                      9196
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG      GLUT1,2                      1756
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT      GLUT1,2                      1756
                                     predictedGroup_RNA2ATAC_clustertype
                                                             <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                              midVen
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                              midVen
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                               GABA1
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                              midVen
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                              midVen
...                                                                  ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG                               GLUT3
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG                             GABA4_2
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC                               GLUT2
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG                               GLUT2
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT                               GLUT2
                                     predictedScore_RNA2ATAC_clustertype
                                                               <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                            1.000000
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                            0.948107
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                            0.850651
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                            0.408128
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                            0.475185
...                                                                  ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG                            0.667286
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG                            0.897909
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC                            0.892677
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG                            0.889763
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT                            0.911827
                                     FINAL_GROUP_LABEL
                                           <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA            midVen
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT            midVen
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG             GABA1
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG            midVen
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC            midVen
...                                                ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG             GLUT3
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG           GABA4_2
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC             GLUT2
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG             GLUT2
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT             GLUT2
In [11]:
table(proj$predictedGroup_RNA2ATAC_clustertype)
table(proj$FINAL_GROUP_LABEL)
proj = saveArchRProject(ArchRProj = proj)

  GABA1 GABA2_1 GABA2_2   GABA3 GABA4_1 GABA4_2   GABA5   GLUT1  GLUT10  GLUT11 
   1078      64    1545     376     967     795    1320    1092     431      39 
  GLUT2   GLUT3   GLUT4   GLUT5   GLUT6   GLUT7   GLUT8   GLUT9  midVen 
   2452    1945     341     992    2195    2283    1157       1    1518 
  GABA1 GABA2_1 GABA2_2   GABA3 GABA4_1 GABA4_2   GABA5   GLUT1  GLUT10  GLUT11 
   1078      64    1545     376     967     795    1320    1092     431      39 
  GLUT2   GLUT3   GLUT4   GLUT5   GLUT6   GLUT7   GLUT8   GLUT9  midVen 
   2452    1945     341     992    2195    2283    1157       1    1518 
Saving ArchRProject...

Loading ArchRProject...

Successfully loaded ArchRProject!


                                                   / |
                                                 /    \
            .                                  /      |.
            \\\                              /        |.
              \\\                          /           `|.
                \\\                      /              |.
                  \                    /                |\
                  \\#####\           /                  ||
                ==###########>      /                   ||
                 \\##==......\    /                     ||
            ______ =       =|__ /__                     ||      \\\
        ,--' ,----`-,__ ___/'  --,-`-===================##========>
       \               '        ##_______ _____ ,--,__,=##,__   ///
        ,    __==    ___,-,__,--'#'  ==='      `-'    | ##,-/
        -,____,---'       \\####\\________________,--\\_##,/
           ___      .______        ______  __    __  .______      
          /   \     |   _  \      /      ||  |  |  | |   _  \     
         /  ^  \    |  |_)  |    |  ,----'|  |__|  | |  |_)  |    
        /  /_\  \   |      /     |  |     |   __   | |      /     
       /  _____  \  |  |\  \\___ |  `----.|  |  |  | |  |\  \\___.
      /__/     \__\ | _| `._____| \______||__|  |__| | _| `._____|
In [ ]:
# MAT <- getMatrixFromProject(
#   ArchRProj = proj,
#   useMatrix = "GeneScoreMatrix",
#   useSeqnames = NULL,
#   verbose = TRUE,
#   binarize = FALSE,
#   threads = getArchRThreads(),
#   logFile = createLogFile("getMatrixFromProject")
# )
In [17]:
# ## # plot the confusion matrix of cell types by predicted cell type clusters
# cM <- confusionMatrix(paste0(proj$Neuron_Type), paste0(proj$ClustersX10))
# cM <- cM / Matrix::colSums(cM)
# cM = cM[,order(colnames(cM))]
# p <- pheatmap::pheatmap(
#   mat = as.matrix(cM), 
#   color = paletteContinuous("whiteBlue"), 
#   border_color = "black")
# p

# preClust <- rownames(cM)[apply(cM, 2 , which.max)]
# cbind(preClust, colnames(cM)) #Assignments
A matrix: 25 × 2 of type chr
preClust
GLUT1,2 C1
GLUT3,4,5,6 C10
GLUT3,4,5,6 C11
GABA2_2, 4_2C12
GABA2_2, 4_2C13
GABA2_1, 4_1C14
GABA? C15
GABA? C16
GABA2_1, 4_1C17
GLUT1,2 C18
GABA5 C19
GLUT8 C2
GABA3 C20
midVent C21
GLUT3,4,5,6 C22
GLUT3,4,5,6 C23
GLUT3,4,5,6 C24
GLUT3,4,5,6 C25
GLUT9,10 C3
GLUT1,2 C4
GLUT1,2 C5
GLUT7,8 C6
GLUT7,8 C7
GLUT3,4,5,6 C8
GLUT7,8 C9
In [ ]:
# library(SingleCellExperiment)
# library(SeuratDisk)



# sce = LoadH5Seurat("/projects/pfenninggroup/singleCell/Macaque_SealDorsalHorn_snATAC-seq/data/tidy_data/mmData.comp.adult.2fixerr.h5seurat",assays = "RNA")
# neuron_data_sce <- as.SingleCellExperiment(sce)
# neuron_data_sce
# counts(neuron_data_sce)
# 2.718 ^ logcounts(neuron_data_sce) - 1
In [16]:
# #manually labelling ATAC clusters, going with RNA integrated labels
# remap = c(
#   'Ex-Cpne4'='GLUT8',
#   'Ex-Maf'='GLUT7,8',
#   'Ex-Prkcg'='GLUT9,10',
#   'Ex-Reln'='GLUT1,2',
#   'Ex-Rreb1'='GLUT11',
#   'Ex-Sox5'='GLUT3,4,5,6',
#   'Inh-Adamts5'='GABA2_2, 4_2', 
#   'Inh-Npy'='GABA3',
#   'Inh-Pdyn'='GABA5',
#   'Inh-Rorb'='GABA2_1, 4_1',
#   'Inh-Cdh3' = 'GABA?',
#   'midVent = midVent' 
# )

# proj$Neuron_Type = mapLabels(proj$predictedGroup_RNA2ATACCo, newLabels = remap, oldLabels = names(remap))
# getCellColData(proj)

The following `from` values were not present in `x`: 


DataFrame with 20591 rows and 36 columns
                                                  Sample TSSEnrichment
                                             <character>     <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA Mouse_DH_SEA2253A58        14.164
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT Mouse_DH_SEA2253A58        15.910
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG Mouse_DH_SEA2253A58        10.861
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG Mouse_DH_SEA2253A58        17.269
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC Mouse_DH_SEA2253A58        18.201
...                                                  ...           ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG Mouse_DH_SEA2253A69         8.303
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG Mouse_DH_SEA2253A69         9.596
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC Mouse_DH_SEA2253A69        50.724
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG Mouse_DH_SEA2253A69        31.498
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT Mouse_DH_SEA2253A69        30.471
                                     ReadsInTSS ReadsInPromoter
                                      <numeric>       <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA       6788           24952
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT       6990           25965
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG       4355           16936
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG       7718           27008
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC       7445           25859
...                                         ...             ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG        348            1581
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG        378            1668
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC       1332            3902
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG       1193            3754
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT        754            2477
                                     ReadsInBlacklist PromoterRatio    PassQC
                                            <numeric>     <numeric> <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA             3777      0.155608         1
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT             3880      0.176551         1
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG             3561      0.115299         1
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG             4147      0.185642         1
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC             5408      0.183335         1
...                                               ...           ...       ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG              244      0.117094         1
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG              202      0.128052         1
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC              340      0.301966         1
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG              240      0.302742         1
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT              247      0.256365         1
                                     NucleosomeRatio nMultiFrags nMonoFrags
                                           <numeric>   <numeric>  <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA        0.919877        6002      41761
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT        1.359279        8719      31168
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG        1.350735        7665      31243
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG        0.868773        4609      38925
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC        0.883453        5368      37444
...                                              ...         ...        ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG        6.054336        1442        957
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG        8.808735        1299        664
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC        0.137300         189       5681
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG        0.130562         152       5484
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT        0.661279         368       2908
                                        nFrags  nDiFrags DoubletScore
                                     <numeric> <numeric>    <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA     80176     32413            0
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT     73534     33647            0
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG     73444     34536            0
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG     72742     29208            0
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC     70524     27712            0
...                                        ...       ...          ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG      6751      4352            0
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG      6513      4550            0
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC      6461       591            0
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG      6200       564            0
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT      4831      1555            0
                                     DoubletEnrichment BlacklistRatio
                                             <numeric>      <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA         0.3000000      0.0235544
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT         0.0666667      0.0263824
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG         0.2666667      0.0242430
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG         0.4000000      0.0285049
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC         0.5666667      0.0383416
...                                                ...            ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG         1.0222222      0.0180714
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG         0.2222222      0.0155074
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC         0.0222222      0.0263117
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG         0.0000000      0.0193548
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT         0.2000000      0.0255641
                                       Sample_ID Date.nuclei.prep
                                     <character>      <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG  SEA2253A58       2022-02-15
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC  SEA2253A58       2022-02-15
...                                          ...              ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG  SEA2253A69       2022-02-23
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG  SEA2253A69       2022-02-23
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC  SEA2253A69       2022-02-23
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG  SEA2253A69       2022-02-23
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT  SEA2253A69       2022-02-23
                                     Biological.rep       Age         Sex
                                        <character> <numeric> <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG     Mouse01-10  0.134247    F/M pool
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC     Mouse01-10  0.134247    F/M pool
...                                             ...       ...         ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG     Mouse11-20  0.156164    F/M pool
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG     Mouse11-20  0.156164    F/M pool
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC     Mouse11-20  0.156164    F/M pool
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG     Mouse11-20  0.156164    F/M pool
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT     Mouse11-20  0.156164    F/M pool
                                         Species      Region ClustersI200
                                     <character> <character>  <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG       Mouse  DorsalHorn          C11
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC       Mouse  DorsalHorn           C9
...                                          ...         ...          ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG       Mouse  DorsalHorn          C14
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG       Mouse  DorsalHorn           C5
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC       Mouse  DorsalHorn          C15
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG       Mouse  DorsalHorn          C15
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT       Mouse  DorsalHorn          C15
                                     ClustersH200 logNFrags   Celltype1
                                      <character> <numeric> <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA          C14   4.90404         EXC
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT          C11   4.86649         EXC
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG          C11   4.86596         EXC
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG          C11   4.86179         EXC
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC          C11   4.84834         EXC
...                                           ...       ...         ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG          C14   3.82937         EXC
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG           C7   3.81378         INH
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC          C15   3.81030         EXC
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG          C15   3.79239         EXC
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT          C15   3.68404         EXC
                                     ClustersX60 predictedCell_Co
                                     <character>      <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA          C6              564
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT          C9             2290
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG         C12                2
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG         C10             4496
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC         C16             1570
...                                          ...              ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG         C22            10242
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG         C17             8674
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC         C20             8839
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG         C20             1590
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT         C20             8839
                                     predictedGroup_RNA2ATACCo
                                                   <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                   midVent
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                   midVent
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                  Inh-Cdh3
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                   midVent
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                  Inh-Rorb
...                                                        ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG                   Ex-Sox5
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG               Inh-Adamts5
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC                   Ex-Reln
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG                   Ex-Reln
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT                   Ex-Reln
                                     predictedScore_RNA2ATACCo ClustersX20
                                                     <numeric> <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                  0.893739          C4
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                  0.805882         C16
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                  0.931563         C11
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                  0.564452          C1
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                  0.537839         C13
...                                                        ...         ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG                  0.665456         C18
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG                  0.949357         C14
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC                  0.819760         C25
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG                  0.991770         C25
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT                  0.881383         C25
                                     ClustersX10 predictedCell_Co_cell
                                     <character>           <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA         C24                   564
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT          C6                  2290
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG         C15                     2
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG         C18                  4496
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC         C17                  1570
...                                          ...                   ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG         C11                 10242
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG         C13                  8674
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC          C5                  8839
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG          C5                  1590
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT          C5                  8839
                                     predictedGroup_RNA2ATACCo_cell
                                                        <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                         midVen
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                         midVen
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                          GABA1
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                         midVen
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                          GABA4
...                                                             ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG                          GLUT4
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG                          GABA4
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC                          GLUT2
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG                          GLUT2
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT                          GLUT2
                                     predictedScore_RNA2ATACCo_cell
                                                          <numeric>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA                       0.893739
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT                       0.805882
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG                       0.931563
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG                       0.564452
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC                       0.413136
...                                                             ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG                       0.551314
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG                       0.918794
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC                       0.636967
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG                       0.909557
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT                       0.705046
                                      Neuron_Type
                                      <character>
Mouse_DH_SEA2253A58#TTACACACTTCGTCAA      midVent
Mouse_DH_SEA2253A58#GCGTGCTGAAGCAGGT      midVent
Mouse_DH_SEA2253A58#CGACCAGACTTCTGAG        GABA?
Mouse_DH_SEA2253A58#TCAGTCCTGAATACAG      midVent
Mouse_DH_SEA2253A58#GCTTTAGGATCGTAAC GABA2_1, 4_1
...                                           ...
Mouse_DH_SEA2253A69#GACCCATCTTAGCAGG  GLUT3,4,5,6
Mouse_DH_SEA2253A69#GACAGGAACTTCTGAG GABA2_2, 4_2
Mouse_DH_SEA2253A69#CTACGTGCTAGGTCCC      GLUT1,2
Mouse_DH_SEA2253A69#ATGTTTCACGCCGTTG      GLUT1,2
Mouse_DH_SEA2253A69#GCGTCGATGGTTGACT      GLUT1,2
In [ ]:
##########################
# library(SingleCellExperiment)
# library(SeuratDisk)

#sce = LoadH5Seurat("/projects/pfenninggroup/singleCell/Macaque_SealDorsalHorn_snATAC-seq/data/tidy_data/mmData.comp.adult.2fixerr.h5seurat",assays = "RNA")
#neuron_data_sce <- as.SingleCellExperiment(sce)

# counts actually natural logcounts, undo first, use `counts` as RNA thing to co-cluster
# counts(neuron_data_sce) = 2.718 ^ logcounts(neuron_data_sce) - 1 
# logcounts(neuron_data_sce) = NULL # so only 1 assay available

#logcounts(neuron_data_sce) = NULL

# has cluster_type data
# table(neuron_data_sce$cluster_type)